Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning
arXiv cs.AI · Hongbin Lin, Sizhe Zou, Juangui Xu, Xinyue Xu, Zhuoli Ouyang, Stanislav Kolchin, Chengwei Qin, Zhongxiang Dai, Yao Shu ·
arXiv:2611.09154v1 Announce Type: new Abstract: Reasoning traces improve vision-language models on complex multimodal tasks, but forcing every input to follow a long reasoning process leads to overthinking and unnecessary inference cost. We study adaptive fast/slow thinking for VLMs, where one model answers…
Excerpt provided by arXiv cs.AI via its public feed. Full reporting belongs to the original publisher.
Read the full story on arXiv cs.AI
Related coverage
TechCrunch AI · 5m ago
PSI is trying to make a business out of AI-driven scientific discovery
The Decoder · 50m ago
Gemini 4 Carbon arrives just in time to feel like yesterdays news in the fastest model cycle yet
Ars Technica AI · 4h ago
DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
Google DeepMind · 7h ago
Introducing AlphaProof Code: a breakthrough in verifying complex software at depth